© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 5479
    Prev
    Next
    INDEX
    Explanations

    phrases related to propositions or proposals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "pro," indicating a focus on proactive or positive concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.72
    inia
    -0.63
     straw
    -0.62
     fault
    -0.62
     fate
    -0.61
     Halls
    -0.61
     needles
    -0.60
     Remastered
    -0.59
     Mellon
    -0.58
     ivory
    -0.58
    POSITIVE LOGITS
    blems
    1.55
    ceed
    1.51
    secut
    1.43
    gressive
    1.43
    spective
    1.34
    hibited
    1.30
    portion
    1.26
    gression
    1.26
    actively
    1.25
    perties
    1.23
    Activations Density 0.018%

    No Known Activations